Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/mayflower/contextmine/claude-mdgit clone --depth 1 https://github.com/mayflower/contextmineWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.03595 | $0.03595 |
| Opus 5 | $0.01798 | $0.01798 |
| Sonnet 5 | $0.00719 | $0.00719 |
| Haiku 4.5 | $0.00360 | $0.00360 |
Grade A, and why
contextmine CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 338 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Build & Development Commands
# Install all Python dependencies (run from repo root)
uv sync --all-packages
# Quality checks (run from repo root)
uv run ruff check . # Linting
uvx ty check # Type checking
uv run pytest -v # Run all tests
# Run a single test
uv run pytest apps/api/tests/test_health.py::test_health_check -v
# Start API server (run from repo root)
uv run uvicorn apps.api.app.main:app --reload --port 8000
# Start frontend dev server (from apps/web)
cd apps/web && npm install && npm run dev
# Docker (full stack)
docker compose up --build
# Database migrations (run from packages/core)
cd packages/core && DATABASE_URL=postgresql+asyncpg://contextmine:contextmine@localhost:5432/contextmine uv run alembic upgrade head
# Run migrations in Docker
docker compose exec api sh -c "cd /app/packages/core && alembic upgrade head"
Architecture Overview
ContextMine is a documentation/code indexing system exposing context via MCP (Model Context Protocol).
Monorepo Structure
- apps/api: FastAPI backend with MCP server mounted at
/mcp - apps/web: React frontend (Vite) admin console
- apps/worker: Prefect worker for background sync jobs
- packages/core: Shared Python library (settings, DB models, services)
- rust/spider_md: Rust-based web crawler binary (HTML→Markdown)
Python Workspace
Uses uv workspaces. The root pyproject.toml defines:
- Workspace members:
apps/api,apps/worker,packages/* - Dev dependencies: ruff, ty, pytest, httpx
- Shared source:
contextmine-corepackage
API Structure
FastAPI app (apps/api/app/main.py) mounts:
- REST routes under
/api/*(health, auth, collections, sources, etc.) - MCP server at
/mcpusing Streamable HTTP transport
MCP exposes tools: get_markdown (semantic search), list_collections, list_documents, outline, find_symbol, definition, references, expand, deep_research.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 338 lines · 3,595 tokens per session scan A 6abf305446cd
contextmine CLAUDE.md is an instructions file published in the GitHub repository mayflower/contextmine (17 stars, last pushed 2mo ago), licensed MIT. It adds 3,595 tokens to every session, about $0.0180 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.